移除思考时的'等一下'类冗余标记，让模型推理更快更准
Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency
- 禁用'Wait''Hmm'等自省标记，减少冗余推理步骤
- 链式思考长度降低27%-51%，在10个任务上保持性能
- 无需修改模型，即插即用，适合多模态推理场景
近期大模型虽能实现复杂分步推理，但常出现过度思考，导致输出冗长低效。本文研究发现，用'Wait''Hmm'等显式自省标记是否必要。提出NoWait方法，在推理阶段抑制这些标记。在文本、视觉、视频共10个基准上测试，五种R1系列模型的链式思考轨迹长度减少27%-51%，且不损害模型能力。NoWait提供了一种无需修改模型即可提升多模态推理效率的即插即用方案。
原文摘要 · Abstract (English)
Recent advances in large reasoning models have enabled complex, step-by-step reasoning but often introduce significant overthinking, resulting in verbose and redundant outputs that hinder efficiency. In this study, we examine whether explicit self-reflection, signaled by tokens such as "Wait" and "Hmm", is necessary for advanced reasoning. We propose NoWait, a simple yet effective approach that disables explicit self-reflection by suppressing these tokens during inference. Extensive experiments on ten benchmarks across textual, visual, and video reasoning tasks show that NoWait reduces chain-of-thought trajectory length by up to 27%-51% in five R1-style model series, without compromising model utility. NoWait thus offers a plug-and-play solution for efficient and utility-preserving multimodal reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。